Merge tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Improve the type checking of request flags (Bart)

 - Ensure queue mapping for a single queues always picks the right queue
   (Bart)

 - Sanitize the io priority handling (Jan)

 - rq-qos race fix (Jinke)

 - Reserved tags handling improvements (John)

 - Separate memory alignment from file/disk offset aligment for O_DIRECT
   (Keith)

 - Add new ublk driver, userspace block driver using io_uring for
   communication with the userspace backend (Ming)

 - Use try_cmpxchg() to cleanup the code in various spots (Uros)

 - Finally remove bdevname() (Christoph)

 - Clean up the zoned device handling (Christoph)

 - Clean up independent access range support (Christoph)

 - Clean up and improve block sysfs handling (Christoph)

 - Clean up and improve teardown of block devices.

   This turns the usual two step process into something that is simpler
   to implement and handle in block drivers (Christoph)

 - Clean up chunk size handling (Christoph)

 - Misc cleanups and fixes (Bart, Bo, Dan, GuoYong, Jason, Keith, Liu,
   Ming, Sebastian, Yang, Ying)

* tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block: (178 commits)
  ublk_drv: fix double shift bug
  ublk_drv: make sure that correct flags(features) returned to userspace
  ublk_drv: fix error handling of ublk_add_dev
  ublk_drv: fix lockdep warning
  block: remove __blk_get_queue
  block: call blk_mq_exit_queue from disk_release for never added disks
  blk-mq: fix error handling in __blk_mq_alloc_disk
  ublk: defer disk allocation
  ublk: rewrite ublk_ctrl_get_queue_affinity to not rely on hctx->cpumask
  ublk: fold __ublk_create_dev into ublk_ctrl_add_dev
  ublk: cleanup ublk_ctrl_uring_cmd
  ublk: simplify ublk_ch_open and ublk_ch_release
  ublk: remove the empty open and release block device operations
  ublk: remove UBLK_IO_F_PREFLUSH
  ublk: add a MAINTAINERS entry
  block: don't allow the same type rq_qos add more than once
  mmc: fix disk/queue leak in case of adding disk failure
  ublk_drv: fix an IS_ERR() vs NULL check
  ublk: remove UBLK_IO_F_INTEGRITY
  ublk_drv: remove unneeded semicolon
  ...

18 files changed, 387 insertions, 265 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 992ee987f273..ca22b06700a9 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -405,7 +405,7 @@ extern void bioset_exit(struct bio_set *);
 extern int biovec_init_pool(mempool_t *pool, int pool_entries);
 
 struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
-			     unsigned int opf, gfp_t gfp_mask,
+			     blk_opf_t opf, gfp_t gfp_mask,
 			     struct bio_set *bs);
 struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask);
 extern void bio_put(struct bio *);
@@ -418,7 +418,7 @@ int bio_init_clone(struct block_device *bdev, struct bio *bio,
 extern struct bio_set fs_bio_set;
 
 static inline struct bio *bio_alloc(struct block_device *bdev,
-		unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask)
+		unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp_mask)
 {
 	return bio_alloc_bioset(bdev, nr_vecs, opf, gfp_mask, &fs_bio_set);
 }
@@ -456,9 +456,9 @@ struct request_queue;
 
 extern int submit_bio_wait(struct bio *bio);
 void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
-	      unsigned short max_vecs, unsigned int opf);
+	      unsigned short max_vecs, blk_opf_t opf);
 extern void bio_uninit(struct bio *);
-void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf);
+void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf);
 void bio_chain(struct bio *, struct bio *);
 
 int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off);
@@ -789,6 +789,6 @@ static inline void bio_clear_polled(struct bio *bio)
 }
 
 struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
-		unsigned int nr_pages, unsigned int opf, gfp_t gfp);
+		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp);
 
 #endif /* __LINUX_BIO_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index e2d9daf7e8dd..effee1dc715a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -57,6 +57,7 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
 /* queue has elevator attached */
 #define RQF_ELV			((__force req_flags_t)(1 << 22))
+#define RQF_RESV			((__force req_flags_t)(1 << 23))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
@@ -79,7 +80,7 @@ struct request {
 	struct blk_mq_ctx *mq_ctx;
 	struct blk_mq_hw_ctx *mq_hctx;
 
-	unsigned int cmd_flags;		/* op and common flags */
+	blk_opf_t cmd_flags;		/* op and common flags */
 	req_flags_t rq_flags;
 
 	int tag;
@@ -197,8 +198,10 @@ struct request {
 	void *end_io_data;
 };
 
-#define req_op(req) \
-	((req)->cmd_flags & REQ_OP_MASK)
+static inline enum req_op req_op(const struct request *req)
+{
+	return req->cmd_flags & REQ_OP_MASK;
+}
 
 static inline bool blk_rq_is_passthrough(struct request *rq)
 {
@@ -519,7 +522,7 @@ struct blk_mq_queue_data {
 	bool last;
 };
 
-typedef bool (busy_tag_iter_fn)(struct request *, void *, bool);
+typedef bool (busy_tag_iter_fn)(struct request *, void *);
 
 /**
  * struct blk_mq_ops - Callback functions that implements block driver
@@ -574,7 +577,7 @@ struct blk_mq_ops {
 	/**
 	 * @timeout: Called on request timeout.
 	 */
-	enum blk_eh_timer_return (*timeout)(struct request *, bool);
+	enum blk_eh_timer_return (*timeout)(struct request *);
 
 	/**
 	 * @poll: Called to poll for completion of a specific tag.
@@ -686,10 +689,12 @@ struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
 									\
 	__blk_mq_alloc_disk(set, queuedata, &__key);			\
 })
+struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
+		struct lock_class_key *lkclass);
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q);
-void blk_mq_unregister_dev(struct device *, struct request_queue *);
+void blk_mq_destroy_queue(struct request_queue *);
 
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set);
 int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
@@ -710,10 +715,10 @@ enum {
 	BLK_MQ_REQ_PM		= (__force blk_mq_req_flags_t)(1 << 2),
 };
 
-struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
+struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf,
 		blk_mq_req_flags_t flags);
 struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
-		unsigned int op, blk_mq_req_flags_t flags,
+		blk_opf_t opf, blk_mq_req_flags_t flags,
 		unsigned int hctx_idx);
 
 /*
@@ -823,6 +828,11 @@ static inline bool blk_mq_need_time_stamp(struct request *rq)
 	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV));
 }
 
+static inline bool blk_mq_is_reserved_rq(struct request *rq)
+{
+	return rq->rq_flags & RQF_RESV;
+}
+
 /*
  * Batched completions only work when there is no I/O error and no special
  * ->end_io handler.
@@ -1121,12 +1131,12 @@ void blk_dump_rq_flags(struct request *, char *);
 #ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_rq_zone_no(struct request *rq)
 {
-	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
+	return disk_zone_no(rq->q->disk, blk_rq_pos(rq));
 }
 
 static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
 {
-	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
+	return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq));
 }
 
 bool blk_req_needs_zone_write_lock(struct request *rq);
@@ -1148,8 +1158,8 @@ static inline void blk_req_zone_write_unlock(struct request *rq)
 
 static inline bool blk_req_zone_is_write_locked(struct request *rq)
 {
-	return rq->q->seq_zones_wlock &&
-		test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock);
+	return rq->q->disk->seq_zones_wlock &&
+		test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock);
 }
 
 static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index a24d4078fb21..1ef99790f6ed 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -240,6 +240,8 @@ static inline void bio_issue_init(struct bio_issue *issue,
 			((u64)size << BIO_ISSUE_SIZE_SHIFT));
 }
 
+typedef __u32 __bitwise blk_opf_t;
+
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE		-1U
 
@@ -250,7 +252,7 @@ typedef unsigned int blk_qc_t;
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
 	struct block_device	*bi_bdev;
-	unsigned int		bi_opf;		/* bottom bits REQ_OP, top bits
+	blk_opf_t		bi_opf;		/* bottom bits REQ_OP, top bits
 						 * req_flags.
 						 */
 	unsigned short		bi_flags;	/* BIO_* below */
@@ -337,8 +339,12 @@ enum {
 
 typedef __u32 __bitwise blk_mq_req_flags_t;
 
-/*
- * Operations and flags common to the bio and request structures.
+#define REQ_OP_BITS	8
+#define REQ_OP_MASK	(__force blk_opf_t)((1 << REQ_OP_BITS) - 1)
+#define REQ_FLAG_BITS	24
+
+/**
+ * enum req_op - Operations common to the bio and request structures.
  * We use 8 bits for encoding the operation, and the remaining 24 for flags.
  *
  * The least significant bit of the operation number indicates the data
@@ -350,41 +356,37 @@ typedef __u32 __bitwise blk_mq_req_flags_t;
  * If a operation does not transfer data the least significant bit has no
  * meaning.
  */
-#define REQ_OP_BITS	8
-#define REQ_OP_MASK	((1 << REQ_OP_BITS) - 1)
-#define REQ_FLAG_BITS	24
-
-enum req_opf {
+enum req_op {
 	/* read sectors from the device */
-	REQ_OP_READ		= 0,
+	REQ_OP_READ		= (__force blk_opf_t)0,
 	/* write sectors to the device */
-	REQ_OP_WRITE		= 1,
+	REQ_OP_WRITE		= (__force blk_opf_t)1,
 	/* flush the volatile write cache */
-	REQ_OP_FLUSH		= 2,
+	REQ_OP_FLUSH		= (__force blk_opf_t)2,
 	/* discard sectors */
-	REQ_OP_DISCARD		= 3,
+	REQ_OP_DISCARD		= (__force blk_opf_t)3,
 	/* securely erase sectors */
-	REQ_OP_SECURE_ERASE	= 5,
+	REQ_OP_SECURE_ERASE	= (__force blk_opf_t)5,
 	/* write the zero filled sector many times */
-	REQ_OP_WRITE_ZEROES	= 9,
+	REQ_OP_WRITE_ZEROES	= (__force blk_opf_t)9,
 	/* Open a zone */
-	REQ_OP_ZONE_OPEN	= 10,
+	REQ_OP_ZONE_OPEN	= (__force blk_opf_t)10,
 	/* Close a zone */
-	REQ_OP_ZONE_CLOSE	= 11,
+	REQ_OP_ZONE_CLOSE	= (__force blk_opf_t)11,
 	/* Transition a zone to full */
-	REQ_OP_ZONE_FINISH	= 12,
+	REQ_OP_ZONE_FINISH	= (__force blk_opf_t)12,
 	/* write data at the current zone write pointer */
-	REQ_OP_ZONE_APPEND	= 13,
+	REQ_OP_ZONE_APPEND	= (__force blk_opf_t)13,
 	/* reset a zone write pointer */
-	REQ_OP_ZONE_RESET	= 15,
+	REQ_OP_ZONE_RESET	= (__force blk_opf_t)15,
 	/* reset all the zone present on the device */
-	REQ_OP_ZONE_RESET_ALL	= 17,
+	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)17,
 
 	/* Driver private requests */
-	REQ_OP_DRV_IN		= 34,
-	REQ_OP_DRV_OUT		= 35,
+	REQ_OP_DRV_IN		= (__force blk_opf_t)34,
+	REQ_OP_DRV_OUT		= (__force blk_opf_t)35,
 
-	REQ_OP_LAST,
+	REQ_OP_LAST		= (__force blk_opf_t)36,
 };
 
 enum req_flag_bits {
@@ -425,28 +427,31 @@ enum req_flag_bits {
 	__REQ_NR_BITS,		/* stops here */
 };
 
-#define REQ_FAILFAST_DEV	(1ULL << __REQ_FAILFAST_DEV)
-#define REQ_FAILFAST_TRANSPORT	(1ULL << __REQ_FAILFAST_TRANSPORT)
-#define REQ_FAILFAST_DRIVER	(1ULL << __REQ_FAILFAST_DRIVER)
-#define REQ_SYNC		(1ULL << __REQ_SYNC)
-#define REQ_META		(1ULL << __REQ_META)
-#define REQ_PRIO		(1ULL << __REQ_PRIO)
-#define REQ_NOMERGE		(1ULL << __REQ_NOMERGE)
-#define REQ_IDLE		(1ULL << __REQ_IDLE)
-#define REQ_INTEGRITY		(1ULL << __REQ_INTEGRITY)
-#define REQ_FUA			(1ULL << __REQ_FUA)
-#define REQ_PREFLUSH		(1ULL << __REQ_PREFLUSH)
-#define REQ_RAHEAD		(1ULL << __REQ_RAHEAD)
-#define REQ_BACKGROUND		(1ULL << __REQ_BACKGROUND)
-#define REQ_NOWAIT		(1ULL << __REQ_NOWAIT)
-#define REQ_CGROUP_PUNT		(1ULL << __REQ_CGROUP_PUNT)
-
-#define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
-#define REQ_POLLED		(1ULL << __REQ_POLLED)
-#define REQ_ALLOC_CACHE		(1ULL << __REQ_ALLOC_CACHE)
-
-#define REQ_DRV			(1ULL << __REQ_DRV)
-#define REQ_SWAP		(1ULL << __REQ_SWAP)
+#define REQ_FAILFAST_DEV	\
+			(__force blk_opf_t)(1ULL << __REQ_FAILFAST_DEV)
+#define REQ_FAILFAST_TRANSPORT	\
+			(__force blk_opf_t)(1ULL << __REQ_FAILFAST_TRANSPORT)
+#define REQ_FAILFAST_DRIVER	\
+			(__force blk_opf_t)(1ULL << __REQ_FAILFAST_DRIVER)
+#define REQ_SYNC	(__force blk_opf_t)(1ULL << __REQ_SYNC)
+#define REQ_META	(__force blk_opf_t)(1ULL << __REQ_META)
+#define REQ_PRIO	(__force blk_opf_t)(1ULL << __REQ_PRIO)
+#define REQ_NOMERGE	(__force blk_opf_t)(1ULL << __REQ_NOMERGE)
+#define REQ_IDLE	(__force blk_opf_t)(1ULL << __REQ_IDLE)
+#define REQ_INTEGRITY	(__force blk_opf_t)(1ULL << __REQ_INTEGRITY)
+#define REQ_FUA		(__force blk_opf_t)(1ULL << __REQ_FUA)
+#define REQ_PREFLUSH	(__force blk_opf_t)(1ULL << __REQ_PREFLUSH)
+#define REQ_RAHEAD	(__force blk_opf_t)(1ULL << __REQ_RAHEAD)
+#define REQ_BACKGROUND	(__force blk_opf_t)(1ULL << __REQ_BACKGROUND)
+#define REQ_NOWAIT	(__force blk_opf_t)(1ULL << __REQ_NOWAIT)
+#define REQ_CGROUP_PUNT	(__force blk_opf_t)(1ULL << __REQ_CGROUP_PUNT)
+
+#define REQ_NOUNMAP	(__force blk_opf_t)(1ULL << __REQ_NOUNMAP)
+#define REQ_POLLED	(__force blk_opf_t)(1ULL << __REQ_POLLED)
+#define REQ_ALLOC_CACHE	(__force blk_opf_t)(1ULL << __REQ_ALLOC_CACHE)
+
+#define REQ_DRV		(__force blk_opf_t)(1ULL << __REQ_DRV)
+#define REQ_SWAP	(__force blk_opf_t)(1ULL << __REQ_SWAP)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
@@ -463,26 +468,28 @@ enum stat_group {
 	NR_STAT_GROUPS
 };
 
-#define bio_op(bio) \
-	((bio)->bi_opf & REQ_OP_MASK)
+static inline enum req_op bio_op(const struct bio *bio)
+{
+	return bio->bi_opf & REQ_OP_MASK;
+}
 
 /* obsolete, don't use in new code */
-static inline void bio_set_op_attrs(struct bio *bio, unsigned op,
-		unsigned op_flags)
+static inline void bio_set_op_attrs(struct bio *bio, enum req_op op,
+				    blk_opf_t op_flags)
 {
 	bio->bi_opf = op | op_flags;
 }
 
-static inline bool op_is_write(unsigned int op)
+static inline bool op_is_write(blk_opf_t op)
 {
-	return (op & 1);
+	return !!(op & (__force blk_opf_t)1);
 }
 
 /*
  * Check if the bio or request is one that needs special treatment in the
  * flush state machine.
  */
-static inline bool op_is_flush(unsigned int op)
+static inline bool op_is_flush(blk_opf_t op)
 {
 	return op & (REQ_FUA | REQ_PREFLUSH);
 }
@@ -492,13 +499,13 @@ static inline bool op_is_flush(unsigned int op)
  * PREFLUSH flag.  Other operations may be marked as synchronous using the
  * REQ_SYNC flag.
  */
-static inline bool op_is_sync(unsigned int op)
+static inline bool op_is_sync(blk_opf_t op)
 {
 	return (op & REQ_OP_MASK) == REQ_OP_READ ||
 		(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
 }
 
-static inline bool op_is_discard(unsigned int op)
+static inline bool op_is_discard(blk_opf_t op)
 {
 	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
 }
@@ -509,7 +516,7 @@ static inline bool op_is_discard(unsigned int op)
  * due to its different handling in the block layer and device response in
  * case of command failure.
  */
-static inline bool op_is_zone_mgmt(enum req_opf op)
+static inline bool op_is_zone_mgmt(enum req_op op)
 {
 	switch (op & REQ_OP_MASK) {
 	case REQ_OP_ZONE_RESET:
@@ -522,7 +529,7 @@ static inline bool op_is_zone_mgmt(enum req_opf op)
 	}
 }
 
-static inline int op_stat_group(unsigned int op)
+static inline int op_stat_group(enum req_op op)
 {
 	if (op_is_discard(op))
 		return STAT_DISCARD;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2f7b43444c5f..d04bdf549efa 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -148,6 +148,7 @@ struct gendisk {
 #define GD_NATIVE_CAPACITY		3
 #define GD_ADDED			4
 #define GD_SUPPRESS_PART_SCAN		5
+#define GD_OWNS_QUEUE			6
 
 	struct mutex open_mutex;	/* open/close mutex */
 	unsigned open_partitions;	/* number of open partitions */
@@ -163,6 +164,29 @@ struct gendisk {
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct kobject integrity_kobj;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
+
+#ifdef CONFIG_BLK_DEV_ZONED
+	/*
+	 * Zoned block device information for request dispatch control.
+	 * nr_zones is the total number of zones of the device. This is always
+	 * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
+	 * bits which indicates if a zone is conventional (bit set) or
+	 * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
+	 * bits which indicates if a zone is write locked, that is, if a write
+	 * request targeting the zone was dispatched.
+	 *
+	 * Reads of this information must be protected with blk_queue_enter() /
+	 * blk_queue_exit(). Modifying this information is only allowed while
+	 * no requests are being processed. See also blk_mq_freeze_queue() and
+	 * blk_mq_unfreeze_queue().
+	 */
+	unsigned int		nr_zones;
+	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
+	unsigned long		*conv_zones_bitmap;
+	unsigned long		*seq_zones_wlock;
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 #if IS_ENABLED(CONFIG_CDROM)
 	struct cdrom_device_info *cdi;
 #endif
@@ -170,6 +194,12 @@ struct gendisk {
 	struct badblocks *bb;
 	struct lockdep_map lockdep_map;
 	u64 diskseq;
+
+	/*
+	 * Independent sector access ranges. This is always NULL for
+	 * devices that do not have multiple independent access ranges.
+	 */
+	struct blk_independent_access_ranges *ia_ranges;
 };
 
 static inline bool disk_live(struct gendisk *disk)
@@ -220,7 +250,7 @@ static inline int blk_validate_block_size(unsigned long bsize)
 	return 0;
 }
 
-static inline bool blk_op_is_passthrough(unsigned int op)
+static inline bool blk_op_is_passthrough(blk_opf_t op)
 {
 	op &= REQ_OP_MASK;
 	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
@@ -284,15 +314,15 @@ struct queue_limits {
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
-void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
+void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
-unsigned int blkdev_nr_zones(struct gendisk *disk);
-extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+unsigned int bdev_nr_zones(struct block_device *bdev);
+extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 			    sector_t sectors, sector_t nr_sectors,
 			    gfp_t gfp_mask);
 int blk_revalidate_disk_zones(struct gendisk *disk,
@@ -305,7 +335,7 @@ extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
-static inline unsigned int blkdev_nr_zones(struct gendisk *disk)
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
 {
 	return 0;
 }
@@ -424,6 +454,11 @@ struct request_queue {
 	unsigned long		nr_requests;	/* Max # of requests */
 
 	unsigned int		dma_pad_mask;
+	/*
+	 * Drivers that set dma_alignment to less than 511 must be prepared to
+	 * handle individual bvec's that are not a multiple of a SECTOR_SIZE
+	 * due to possible offsets.
+	 */
 	unsigned int		dma_alignment;
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
@@ -455,31 +490,6 @@ struct request_queue {
 
 	unsigned int		required_elevator_features;
 
-#ifdef CONFIG_BLK_DEV_ZONED
-	/*
-	 * Zoned block device information for request dispatch control.
-	 * nr_zones is the total number of zones of the device. This is always
-	 * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
-	 * bits which indicates if a zone is conventional (bit set) or
-	 * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
-	 * bits which indicates if a zone is write locked, that is, if a write
-	 * request targeting the zone was dispatched. All three fields are
-	 * initialized by the low level device driver (e.g. scsi/sd.c).
-	 * Stacking drivers (device mappers) may or may not initialize
-	 * these fields.
-	 *
-	 * Reads of this information must be protected with blk_queue_enter() /
-	 * blk_queue_exit(). Modifying this information is only allowed while
-	 * no requests are being processed. See also blk_mq_freeze_queue() and
-	 * blk_mq_unfreeze_queue().
-	 */
-	unsigned int		nr_zones;
-	unsigned long		*conv_zones_bitmap;
-	unsigned long		*seq_zones_wlock;
-	unsigned int		max_open_zones;
-	unsigned int		max_active_zones;
-#endif /* CONFIG_BLK_DEV_ZONED */
-
 	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
@@ -533,12 +543,6 @@ struct request_queue {
 
 	bool			mq_sysfs_init_done;
 
-	/*
-	 * Independent sector access ranges. This is always NULL for
-	 * devices that do not have multiple independent access ranges.
-	 */
-	struct blk_independent_access_ranges *ia_ranges;
-
 	/**
 	 * @srcu: Sleepable RCU. Use as lock when type of the request queue
 	 * is blocking (BLK_MQ_F_BLOCKING). Must be the last member
@@ -559,7 +563,6 @@ struct request_queue {
 #define QUEUE_FLAG_NOXMERGES	9	/* No extended merges */
 #define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
-#define QUEUE_FLAG_DEAD		13	/* queue tear-down finished */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
 #define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
 #define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
@@ -587,7 +590,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
 #define blk_queue_has_srcu(q)	test_bit(QUEUE_FLAG_HAS_SRCU, &(q)->queue_flags)
-#define blk_queue_dead(q)	test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags)
 #define blk_queue_init_done(q)	test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
@@ -663,76 +665,69 @@ static inline bool blk_queue_is_zoned(struct request_queue *q)
 	}
 }
 
-static inline sector_t blk_queue_zone_sectors(struct request_queue *q)
-{
-	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
-}
-
 #ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
-	return blk_queue_is_zoned(q) ? q->nr_zones : 0;
+	return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0;
 }
 
-static inline unsigned int blk_queue_zone_no(struct request_queue *q,
-					     sector_t sector)
+static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
-	if (!blk_queue_is_zoned(q))
+	if (!blk_queue_is_zoned(disk->queue))
 		return 0;
-	return sector >> ilog2(q->limits.chunk_sectors);
+	return sector >> ilog2(disk->queue->limits.chunk_sectors);
 }
 
-static inline bool blk_queue_zone_is_seq(struct request_queue *q,
-					 sector_t sector)
+static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
 {
-	if (!blk_queue_is_zoned(q))
+	if (!blk_queue_is_zoned(disk->queue))
 		return false;
-	if (!q->conv_zones_bitmap)
+	if (!disk->conv_zones_bitmap)
 		return true;
-	return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap);
+	return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
 }
 
-static inline void blk_queue_max_open_zones(struct request_queue *q,
+static inline void disk_set_max_open_zones(struct gendisk *disk,
 		unsigned int max_open_zones)
 {
-	q->max_open_zones = max_open_zones;
+	disk->max_open_zones = max_open_zones;
 }
 
-static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+static inline void disk_set_max_active_zones(struct gendisk *disk,
+		unsigned int max_active_zones)
 {
-	return q->max_open_zones;
+	disk->max_active_zones = max_active_zones;
 }
 
-static inline void blk_queue_max_active_zones(struct request_queue *q,
-		unsigned int max_active_zones)
+static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
-	q->max_active_zones = max_active_zones;
+	return bdev->bd_disk->max_open_zones;
 }
 
-static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
-	return q->max_active_zones;
+	return bdev->bd_disk->max_active_zones;
 }
+
 #else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
 }
-static inline bool blk_queue_zone_is_seq(struct request_queue *q,
-					 sector_t sector)
+static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
 {
 	return false;
 }
-static inline unsigned int blk_queue_zone_no(struct request_queue *q,
-					     sector_t sector)
+static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
 	return 0;
 }
-static inline unsigned int queue_max_open_zones(const struct request_queue *q)
+static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
 	return 0;
 }
-static inline unsigned int queue_max_active_zones(const struct request_queue *q)
+
+static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
 	return 0;
 }
@@ -812,8 +807,6 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
 
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
 
-struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
-		struct lock_class_key *lkclass);
 void put_disk(struct gendisk *disk);
 struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
 
@@ -832,7 +825,6 @@ struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
 									\
 	__blk_alloc_disk(node_id, &__key);				\
 })
-void blk_cleanup_disk(struct gendisk *disk);
 
 int __register_blkdev(unsigned int major, const char *name,
 		void (*probe)(dev_t devt));
@@ -880,7 +872,7 @@ extern void blk_queue_exit(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
 
 /* Helper to convert REQ_OP_XXX to its string format XXX */
-extern const char *blk_op_str(unsigned int op);
+extern const char *blk_op_str(enum req_op op);
 
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
@@ -898,64 +890,33 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
 	return bdev->bd_queue;	/* this is never NULL */
 }
 
-#ifdef CONFIG_BLK_DEV_ZONED
-
 /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
 const char *blk_zone_cond_str(enum blk_zone_cond zone_cond);
 
 static inline unsigned int bio_zone_no(struct bio *bio)
 {
-	return blk_queue_zone_no(bdev_get_queue(bio->bi_bdev),
-				 bio->bi_iter.bi_sector);
+	return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
 }
 
 static inline unsigned int bio_zone_is_seq(struct bio *bio)
 {
-	return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev),
-				     bio->bi_iter.bi_sector);
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
-static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
-						     int op)
-{
-	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
-		return min(q->limits.max_discard_sectors,
-			   UINT_MAX >> SECTOR_SHIFT);
-
-	if (unlikely(op == REQ_OP_WRITE_ZEROES))
-		return q->limits.max_write_zeroes_sectors;
-
-	return q->limits.max_sectors;
+	return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
 }
 
 /*
- * Return maximum size of a request at given offset. Only valid for
- * file system requests.
+ * Return how much of the chunk is left to be used for I/O at a given offset.
  */
-static inline unsigned int blk_max_size_offset(struct request_queue *q,
-					       sector_t offset,
-					       unsigned int chunk_sectors)
-{
-	if (!chunk_sectors) {
-		if (q->limits.chunk_sectors)
-			chunk_sectors = q->limits.chunk_sectors;
-		else
-			return q->limits.max_sectors;
-	}
-
-	if (likely(is_power_of_2(chunk_sectors)))
-		chunk_sectors -= offset & (chunk_sectors - 1);
-	else
-		chunk_sectors -= sector_div(offset, chunk_sectors);
-
-	return min(q->limits.max_sectors, chunk_sectors);
+static inline unsigned int blk_chunk_sectors_left(sector_t offset,
+		unsigned int chunk_sectors)
+{
+	if (unlikely(!is_power_of_2(chunk_sectors)))
+		return chunk_sectors - sector_div(offset, chunk_sectors);
+	return chunk_sectors - (offset & (chunk_sectors - 1));
 }
 
 /*
  * Access functions for manipulating queue properties
  */
-extern void blk_cleanup_queue(struct request_queue *);
 void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
@@ -1337,32 +1298,26 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (q)
-		return blk_queue_zone_sectors(q);
-	return 0;
+	if (!blk_queue_is_zoned(q))
+		return 0;
+	return q->limits.chunk_sectors;
 }
 
-static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
+static inline int queue_dma_alignment(const struct request_queue *q)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return queue_max_open_zones(q);
-	return 0;
+	return q ? q->dma_alignment : 511;
 }
 
-static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
+static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return queue_max_active_zones(q);
-	return 0;
+	return queue_dma_alignment(bdev_get_queue(bdev));
 }
 
-static inline int queue_dma_alignment(const struct request_queue *q)
+static inline bool bdev_iter_is_aligned(struct block_device *bdev,
+					struct iov_iter *iter)
 {
-	return q ? q->dma_alignment : 511;
+	return iov_iter_is_aligned(iter, bdev_dma_alignment(bdev),
+				   bdev_logical_block_size(bdev) - 1);
 }
 
 static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
@@ -1426,7 +1381,7 @@ struct block_device_operations {
 			unsigned int flags);
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
-	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, enum req_op);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
@@ -1479,9 +1434,9 @@ static inline void blk_wake_io_task(struct task_struct *waiter)
 }
 
 unsigned long bdev_start_io_acct(struct block_device *bdev,
-				 unsigned int sectors, unsigned int op,
+				 unsigned int sectors, enum req_op op,
 				 unsigned long start_time);
-void bdev_end_io_acct(struct block_device *bdev, unsigned int op,
+void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
 		unsigned long start_time);
 
 void bio_start_io_acct_time(struct bio *bio, unsigned long start_time);
@@ -1502,7 +1457,6 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 int bdev_read_only(struct block_device *bdev);
 int set_blocksize(struct block_device *bdev, int size);
 
-const char *bdevname(struct block_device *bdev, char *buffer);
 int lookup_bdev(const char *pathname, dev_t *dev);
 
 void blkdev_show(struct seq_file *seqf, off_t offset);
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 623e22492afa..cfbda114348c 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -7,6 +7,7 @@
 #include <linux/compat.h>
 #include <uapi/linux/blktrace_api.h>
 #include <linux/list.h>
+#include <linux/blk_types.h>
 
 #if defined(CONFIG_BLK_DEV_IO_TRACE)
 
@@ -77,10 +78,6 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 			   char __user *arg);
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
-extern void blk_trace_remove_sysfs(struct device *dev);
-extern int blk_trace_init_sysfs(struct device *dev);
-
-extern struct attribute_group blk_trace_attr_group;
 
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 # define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
@@ -91,13 +88,7 @@ extern struct attribute_group blk_trace_attr_group;
 # define blk_trace_remove(q)				(-ENOTTY)
 # define blk_add_trace_msg(q, fmt, ...)			do { } while (0)
 # define blk_add_cgroup_trace_msg(q, cg, fmt, ...)	do { } while (0)
-# define blk_trace_remove_sysfs(dev)			do { } while (0)
 # define blk_trace_note_message_enabled(q)		(false)
-static inline int blk_trace_init_sysfs(struct device *dev)
-{
-	return 0;
-}
-
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_COMPAT
@@ -115,7 +106,7 @@ struct compat_blk_user_trace_setup {
 
 #endif
 
-void blk_fill_rwbs(char *rwbs, unsigned int op);
+void blk_fill_rwbs(char *rwbs, blk_opf_t opf);
 
 static inline sector_t blk_rq_trace_sector(struct request *rq)
 {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index c9d1463bb20f..bb68eb6407da 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -9,6 +9,7 @@
 #define _LINUX_BUFFER_HEAD_H
 
 #include <linux/types.h>
+#include <linux/blk_types.h>
 #include <linux/fs.h>
 #include <linux/linkage.h>
 #include <linux/pagemap.h>
@@ -201,11 +202,11 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
 void __lock_buffer(struct buffer_head *bh);
-void ll_rw_block(int, int, int, struct buffer_head * bh[]);
+void ll_rw_block(blk_opf_t, int, struct buffer_head * bh[]);
 int sync_dirty_buffer(struct buffer_head *bh);
-int __sync_dirty_buffer(struct buffer_head *bh, int op_flags);
-void write_dirty_buffer(struct buffer_head *bh, int op_flags);
-int submit_bh(int, int, struct buffer_head *);
+int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
+void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags);
+int submit_bh(blk_opf_t, struct buffer_head *);
 void write_boundary_block(struct block_device *bdev,
 			sector_t bblock, unsigned blocksize);
 int bh_uptodate_or_lock(struct buffer_head *bh);
diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h
index a52c6580cc9a..8e1c4ab5df04 100644
--- a/include/linux/dm-io.h
+++ b/include/linux/dm-io.h
@@ -13,6 +13,7 @@
 #ifdef __KERNEL__
 
 #include <linux/types.h>
+#include <linux/blk_types.h>
 
 struct dm_io_region {
 	struct block_device *bdev;
@@ -57,8 +58,7 @@ struct dm_io_notify {
  */
 struct dm_io_client;
 struct dm_io_request {
-	int bi_op;			/* REQ_OP */
-	int bi_op_flags;		/* req_flag_bits */
+	blk_opf_t	    bi_opf;	/* Request type and flags */
 	struct dm_io_memory mem;	/* Memory to use for io */
 	struct dm_io_notify notify;	/* Synchronous if notify.fn is NULL */
 	struct dm_io_client *client;	/* Client memory handler */
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index 3f53bc27a19b..7578d4f6a969 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -11,7 +11,7 @@
 /*
  * Default IO priority.
  */
-#define IOPRIO_DEFAULT	IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM)
+#define IOPRIO_DEFAULT	IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0)
 
 /*
  * Check that a priority value has a valid class.
@@ -46,23 +46,19 @@ static inline int task_nice_ioclass(struct task_struct *task)
 		return IOPRIO_CLASS_BE;
 }
 
-/*
- * If the calling process has set an I/O priority, use that. Otherwise, return
- * the default I/O priority.
- */
-static inline int get_current_ioprio(void)
+#ifdef CONFIG_BLOCK
+int __get_task_ioprio(struct task_struct *p);
+#else
+static inline int __get_task_ioprio(struct task_struct *p)
 {
-	struct io_context *ioc = current->io_context;
-
-	if (ioc)
-		return ioc->ioprio;
 	return IOPRIO_DEFAULT;
 }
+#endif /* CONFIG_BLOCK */
 
-/*
- * For inheritance, return the highest of the two given priorities
- */
-extern int ioprio_best(unsigned short aprio, unsigned short bprio);
+static inline int get_current_ioprio(void)
+{
+	return __get_task_ioprio(current);
+}
 
 extern int set_task_ioprio(struct task_struct *task, int ioprio);
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index e79d6e0b14e8..dc1724131300 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1557,7 +1557,7 @@ extern int	   jbd2_journal_wipe       (journal_t *, int);
 extern int	   jbd2_journal_skip_recovery	(journal_t *);
 extern void	   jbd2_journal_update_sb_errno(journal_t *);
 extern int	   jbd2_journal_update_sb_log_tail	(journal_t *, tid_t,
-				unsigned long, int);
+				unsigned long, blk_opf_t);
 extern void	   jbd2_journal_abort      (journal_t *, int);
 extern int	   jbd2_journal_errno      (journal_t *);
 extern void	   jbd2_journal_ack_err    (journal_t *);
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 739285fe5a2f..34ba4a731179 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -219,6 +219,8 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 #endif
 
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
+bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask,
+			unsigned len_mask);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 unsigned long iov_iter_gap_alignment(const struct iov_iter *i);
 void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index b8c9610c2313..3f045f6d6c4f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -101,9 +101,9 @@ struct writeback_control {
 #endif
 };
 
-static inline int wbc_to_write_flags(struct writeback_control *wbc)
+static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc)
 {
-	int flags = 0;
+	blk_opf_t flags = 0;
 
 	if (wbc->punt_to_cgroup)
 		flags = REQ_CGROUP_PUNT;
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 1e80e70dfa92..bac55decf900 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -386,7 +386,7 @@ static inline unsigned scsi_transfer_length(struct scsi_cmnd *scmd)
 extern void scsi_build_sense(struct scsi_cmnd *scmd, int desc,
 			     u8 key, u8 asc, u8 ascq);
 
-struct request *scsi_alloc_request(struct request_queue *q,
-		unsigned int op, blk_mq_req_flags_t flags);
+struct request *scsi_alloc_request(struct request_queue *q, blk_opf_t opf,
+				   blk_mq_req_flags_t flags);
 
 #endif /* _SCSI_SCSI_CMND_H */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 7cf5f3b7589f..2493bd65351a 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -457,7 +457,7 @@ extern void scsi_sanitize_inquiry_string(unsigned char *s, int len);
 extern int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			int data_direction, void *buffer, unsigned bufflen,
 			unsigned char *sense, struct scsi_sense_hdr *sshdr,
-			int timeout, int retries, u64 flags,
+			int timeout, int retries, blk_opf_t flags,
 			req_flags_t rq_flags, int *resid);
 /* Make sure any sense buffer is the correct size. */
 #define scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,	\
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 667d889b92b5..65082ecdd557 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -786,7 +786,7 @@ extern int scsi_host_block(struct Scsi_Host *shost);
 extern int scsi_host_unblock(struct Scsi_Host *shost, int new_state);
 
 void scsi_host_busy_iter(struct Scsi_Host *,
-			 bool (*fn)(struct scsi_cmnd *, void *, bool), void *priv);
+			 bool (*fn)(struct scsi_cmnd *, void *), void *priv);
 
 struct class_container;
 
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 513e889ef8aa..f1e922237736 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -66,7 +66,7 @@ TRACE_DEFINE_ENUM(CP_RESIZE);
 
 #define F2FS_OP_FLAGS (REQ_RAHEAD | REQ_SYNC | REQ_META | REQ_PRIO |	\
 			REQ_PREFLUSH | REQ_FUA)
-#define F2FS_BIO_FLAG_MASK(t)	(t & F2FS_OP_FLAGS)
+#define F2FS_BIO_FLAG_MASK(t) (__force u32)((t) & F2FS_OP_FLAGS)
 
 #define show_bio_type(op,op_flags)	show_bio_op(op),		\
 						show_bio_op_flags(op_flags)
@@ -75,12 +75,12 @@ TRACE_DEFINE_ENUM(CP_RESIZE);
 
 #define show_bio_op_flags(flags)					\
 	__print_flags(F2FS_BIO_FLAG_MASK(flags), "|",			\
-		{ REQ_RAHEAD,		"R" },				\
-		{ REQ_SYNC,		"S" },				\
-		{ REQ_META,		"M" },				\
-		{ REQ_PRIO,		"P" },				\
-		{ REQ_PREFLUSH,		"PF" },				\
-		{ REQ_FUA,		"FUA" })
+		{ (__force u32)REQ_RAHEAD,	"R" },			\
+		{ (__force u32)REQ_SYNC,	"S" },			\
+		{ (__force u32)REQ_META,	"M" },			\
+		{ (__force u32)REQ_PRIO,	"P" },			\
+		{ (__force u32)REQ_PREFLUSH,	"PF" },			\
+		{ (__force u32)REQ_FUA,		"FUA" })
 
 #define show_data_type(type)						\
 	__print_symbolic(type,						\
@@ -1036,8 +1036,8 @@ DECLARE_EVENT_CLASS(f2fs__submit_page_bio,
 		__field(pgoff_t, index)
 		__field(block_t, old_blkaddr)
 		__field(block_t, new_blkaddr)
-		__field(int, op)
-		__field(int, op_flags)
+		__field(enum req_op, op)
+		__field(blk_opf_t, op_flags)
 		__field(int, temp)
 		__field(int, type)
 	),
@@ -1092,8 +1092,8 @@ DECLARE_EVENT_CLASS(f2fs__bio,
 	TP_STRUCT__entry(
 		__field(dev_t,	dev)
 		__field(dev_t,	target)
-		__field(int,	op)
-		__field(int,	op_flags)
+		__field(enum req_op,	op)
+		__field(blk_opf_t,	op_flags)
 		__field(int,	type)
 		__field(sector_t,	sector)
 		__field(unsigned int,	size)
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index a4dfe005983d..99f783c384bb 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -355,22 +355,22 @@ TRACE_EVENT(jbd2_update_log_tail,
 
 TRACE_EVENT(jbd2_write_superblock,
 
-	TP_PROTO(journal_t *journal, int write_op),
+	TP_PROTO(journal_t *journal, blk_opf_t write_flags),
 
-	TP_ARGS(journal, write_op),
+	TP_ARGS(journal, write_flags),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,  dev			)
-		__field(	  int,  write_op		)
+		__field(    blk_opf_t,  write_flags		)
 	),
 
 	TP_fast_assign(
 		__entry->dev		= journal->j_fs_dev->bd_dev;
-		__entry->write_op	= write_op;
+		__entry->write_flags	= write_flags;
 	),
 
-	TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev),
-		  MINOR(__entry->dev), __entry->write_op)
+	TP_printk("dev %d,%d write_flags %x", MAJOR(__entry->dev),
+		  MINOR(__entry->dev), (__force u32)__entry->write_flags)
 );
 
 TRACE_EVENT(jbd2_lock_buffer_stall,
diff --git a/include/trace/events/nilfs2.h b/include/trace/events/nilfs2.h
index 84ee31fc04cc..8efc6236f57c 100644
--- a/include/trace/events/nilfs2.h
+++ b/include/trace/events/nilfs2.h
@@ -192,7 +192,7 @@ TRACE_EVENT(nilfs2_mdt_submit_block,
 	    TP_PROTO(struct inode *inode,
 		     unsigned long ino,
 		     unsigned long blkoff,
-		     int mode),
+		     enum req_op mode),
 
 	    TP_ARGS(inode, ino, blkoff, mode),
 
@@ -200,7 +200,7 @@ TRACE_EVENT(nilfs2_mdt_submit_block,
 		    __field(struct inode *, inode)
 		    __field(unsigned long, ino)
 		    __field(unsigned long, blkoff)
-		    __field(int, mode)
+		    __field(enum req_op, mode)
 	    ),
 
 	    TP_fast_assign(
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
new file mode 100644
index 000000000000..ca33092354ab
--- /dev/null
+++ b/include/uapi/linux/ublk_cmd.h
@@ -0,0 +1,161 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef USER_BLK_DRV_CMD_INC_H
+#define USER_BLK_DRV_CMD_INC_H
+
+#include <linux/types.h>
+
+/* ublk server command definition */
+
+/*
+ * Admin commands, issued by ublk server, and handled by ublk driver.
+ */
+#define	UBLK_CMD_GET_QUEUE_AFFINITY	0x01
+#define	UBLK_CMD_GET_DEV_INFO	0x02
+#define	UBLK_CMD_ADD_DEV		0x04
+#define	UBLK_CMD_DEL_DEV		0x05
+#define	UBLK_CMD_START_DEV	0x06
+#define	UBLK_CMD_STOP_DEV	0x07
+
+/*
+ * IO commands, issued by ublk server, and handled by ublk driver.
+ *
+ * FETCH_REQ: issued via sqe(URING_CMD) beforehand for fetching IO request
+ *      from ublk driver, should be issued only when starting device. After
+ *      the associated cqe is returned, request's tag can be retrieved via
+ *      cqe->userdata.
+ *
+ * COMMIT_AND_FETCH_REQ: issued via sqe(URING_CMD) after ublkserver handled
+ *      this IO request, request's handling result is committed to ublk
+ *      driver, meantime FETCH_REQ is piggyback, and FETCH_REQ has to be
+ *      handled before completing io request.
+ */
+#define	UBLK_IO_FETCH_REQ		0x20
+#define	UBLK_IO_COMMIT_AND_FETCH_REQ	0x21
+
+/* only ABORT means that no re-fetch */
+#define UBLK_IO_RES_OK			0
+#define UBLK_IO_RES_ABORT		(-ENODEV)
+
+#define UBLKSRV_CMD_BUF_OFFSET	0
+#define UBLKSRV_IO_BUF_OFFSET	0x80000000
+
+/* tag bit is 12bit, so at most 4096 IOs for each queue */
+#define UBLK_MAX_QUEUE_DEPTH	4096
+
+/*
+ * zero copy requires 4k block size, and can remap ublk driver's io
+ * request into ublksrv's vm space
+ */
+#define UBLK_F_SUPPORT_ZERO_COPY	(1ULL << 0)
+
+/*
+ * Force to complete io cmd via io_uring_cmd_complete_in_task so that
+ * performance comparison is done easily with using task_work_add
+ */
+#define UBLK_F_URING_CMD_COMP_IN_TASK	(1ULL << 1)
+
+/* device state */
+#define UBLK_S_DEV_DEAD	0
+#define UBLK_S_DEV_LIVE	1
+
+/* shipped via sqe->cmd of io_uring command */
+struct ublksrv_ctrl_cmd {
+	/* sent to which device, must be valid */
+	__u32	dev_id;
+
+	/* sent to which queue, must be -1 if the cmd isn't for queue */
+	__u16	queue_id;
+	/*
+	 * cmd specific buffer, can be IN or OUT.
+	 */
+	__u16	len;
+	__u64	addr;
+
+	/* inline data */
+	__u64	data[2];
+};
+
+struct ublksrv_ctrl_dev_info {
+	__u16	nr_hw_queues;
+	__u16	queue_depth;
+	__u16	block_size;
+	__u16	state;
+
+	__u32	rq_max_blocks;
+	__u32	dev_id;
+
+	__u64   dev_blocks;
+
+	__s32	ublksrv_pid;
+	__s32	reserved0;
+	__u64	flags;
+	__u64	flags_reserved;
+
+	/* For ublksrv internal use, invisible to ublk driver */
+	__u64	ublksrv_flags;
+	__u64	reserved1[9];
+};
+
+#define		UBLK_IO_OP_READ		0
+#define		UBLK_IO_OP_WRITE		1
+#define		UBLK_IO_OP_FLUSH		2
+#define		UBLK_IO_OP_DISCARD	3
+#define		UBLK_IO_OP_WRITE_SAME	4
+#define		UBLK_IO_OP_WRITE_ZEROES	5
+
+#define		UBLK_IO_F_FAILFAST_DEV		(1U << 8)
+#define		UBLK_IO_F_FAILFAST_TRANSPORT	(1U << 9)
+#define		UBLK_IO_F_FAILFAST_DRIVER	(1U << 10)
+#define		UBLK_IO_F_META			(1U << 11)
+#define		UBLK_IO_F_FUA			(1U << 13)
+#define		UBLK_IO_F_NOUNMAP		(1U << 15)
+#define		UBLK_IO_F_SWAP			(1U << 16)
+
+/*
+ * io cmd is described by this structure, and stored in share memory, indexed
+ * by request tag.
+ *
+ * The data is stored by ublk driver, and read by ublksrv after one fetch command
+ * returns.
+ */
+struct ublksrv_io_desc {
+	/* op: bit 0-7, flags: bit 8-31 */
+	__u32		op_flags;
+
+	__u32		nr_sectors;
+
+	/* start sector for this io */
+	__u64		start_sector;
+
+	/* buffer address in ublksrv daemon vm space, from ublk driver */
+	__u64		addr;
+};
+
+static inline __u8 ublksrv_get_op(const struct ublksrv_io_desc *iod)
+{
+	return iod->op_flags & 0xff;
+}
+
+static inline __u32 ublksrv_get_flags(const struct ublksrv_io_desc *iod)
+{
+	return iod->op_flags >> 8;
+}
+
+/* issued to ublk driver via /dev/ublkcN */
+struct ublksrv_io_cmd {
+	__u16	q_id;
+
+	/* for fetch/commit which result */
+	__u16	tag;
+
+	/* io result, it is valid for COMMIT* command only */
+	__s32	result;
+
+	/*
+	 * userspace buffer address in ublksrv daemon process, valid for
+	 * FETCH* command only
+	 */
+	__u64	addr;
+};
+
+#endif